INDEX

Explanations

terms related to knowledge

oai_token-act-pair · gpt-3.5-turbo

references to the concept of knowledge

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 5-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.5.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.5.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ishable

-0.64

onies

-0.63

coni

-0.62

avored

-0.62

gg

-0.61

issions

-0.60

gm

-0.60

etheus

-0.59

agraph

-0.59

interstitial

-0.59

POSITIVE LOGITS

ledge

1.20

lege

1.13

fulness

0.87

ledged

0.85

fully

0.82

ellect

0.78

 knowledge

0.78

llor

0.77

reading

0.76

 comprehension

0.75

Activations Density 0.023%

terms related to knowledge

references to the concept of knowledge

No Comments

No Known Activations